|
Vol.14, No.4, November 2025. ISSN: 2217-8309 eISSN: 2217-8333
TEM Journal
TECHNOLOGY, EDUCATION, MANAGEMENT, INFORMATICS Association for Information Communication Technology Education and Science |
Analysis of Dynamic Financial Performance of Airline Companies Using an Algorithm Combining Genetic Algorithm and DTW Clustering
Stefan Milojević, Tijana Matejić, Snežana Knežević
© 2025 Stefan Milojević, published by UIKTEN. This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License. (CC BY-NC-ND 4.0)
Citation Information: TEM Journal. Volume 14, Issue 4, Pages 2895-2910, ISSN 2217-8309, DOI: 10.18421/TEM144-01, November 2025.
Received: 20 June 2025. Revised: 30 September 2025.
Abstract:
Air transport underpins modern mobility, trade and tourism making it a strategic pillar of the transport sector. Yet airlines often operate with fragile financial structures, underscoring the need for rigorous assessment of their financial performance. The literature features numerous studies that examine airlines’ financial performances and conduct mutual comparisons by constructing single composite indices based on financial indicators. To the best of the knowledge, no previous study has examined similarity and outlier detection among airlines based on the temporal dynamics of their financial performance indicators, nor has it conducted a financial analysis of the passenger airlines in Serbia. To accomplish the first objective, using financial statement data including 27 indicators for 15 airlines operating in the country for the 2021–2024 period, the study introduces purpose-built algorithm for the time-series-clustering. The algorithm integrates DTW-based k-means clustering and a Genetic Algorithm, identifies the most discriminative indicators between airline groups and yields sharper inter-cluster separation, and thereby more reliable similarity and outlier analysis than classical time-series clustering methods. Addressing the second objective, the evidence indicates recovery from the COVID-19 crisis in Serbia’s passenger air transport sector without sustained growth, calling for ongoing monitoring and targeted liquidity and resource allocation interventions.
Keywords – Dynamic Time Warping, genetic algorithm, clustering, financial performance, outlier detection. |
|
----------------------------------------------------------------------------------------------------------- ----------------------------------------------------------------------------------------------------------- |